Machine Learning Approach to Detect Congenital Heart Diseases using Angle at Axial Triradius

In this paper, we propose a machine learning method to detect Congenital Heart Diseases using a palm pattern known as axial triradius. An Axial triradius is one of the features of palm whose position can be used to detect Congenital Heart Diseases. First, a machine learning based method has been proposed to identify triradii on palm image. Method has been proposed to find the angle at axial triradius using leftmost, rightmost and axial triradii. The range of angle at axial triradius is used to detect different Congenital Heart Diseases. The proposed method can be used to detect the Congenital Heart Diseases such as Tetralogy of Fallot, Atrial Septal Defect, Ventricular Septal Defect and Coarctation of the Aorta. The proposed method has achieved an accuracy of 89.60% in the detection of the triradii and an accuracy of 89.68% in the detection of leftmost, rightmost and axial triradii. Secondly, calculation of axial triradius for the palm images of the patients suffering from Tetralogy of Fallot, Atrial Septal Defect, Ventricular Septal Defect and Coarctation of Aorta has been done. The results obtained have shown that the proposed method can be used as a screening method to detect Congenital Heart Diseases with axial triradius.